摘要
The diagnosis of Parkinson's disease and atypical Parkinsonism remains clinically difficult, especially at the early stage of the disease, since there is a significant overlap of symptoms. Multimodal MRI has significantly improved diagnostic accuracy and understanding of the pathophysiology of Parkinsonian disorders. Structural and quantitative MRI sequences provide biomarkers sensitive to different tissue properties that detect abnormalities specific to each disease and contribute to the diagnosis. Machine learning techniques using these MRI biomarkers can effectively differentiate atypical Parkinsonian syndromes. Such approaches could be implemented in a clinical environment and improve the management of Parkinsonian patients. This review presents different structural and quantitative MRI techniques, their contribution to the differential diagnosis of atypical Parkinsonian disorders and their interest for individual-level diagnosis.
学科与关键词
- Mining imaging and clinical data with machine learning approaches for the diagnosis and early detection of Parkinson's diseaseZhang, Jing*npj Parkinsons Disease, 2022, 8(1): 13.被引 24
- MRI biomarkers of motor and non-motor symptoms in Parkinson's diseaseRyman, Sephira G.; Poston, Kathleen L.*PARKINSONISM & RELATED DISORDERS, 2020, 73: 85-93.被引 52
- Deep learning to differentiate parkinsonian disorders separately using single midsagittal MR imaging: a proof of concept studyKiryu, Shigeru*; Yasaka, Koichiro; Akai, Hiroyuki; Nakata, Yasuhiro; Sugomori, Yusuke; Hara, Seigo; Seo, Maria; Abe, Osamu; Ohtomo, KuniEuropean Radiology, 2019, 29(12): 6891-6899.被引 46
